2020/10/23 by Dave Braines, Federico Cerutti, Braines, Dave +10
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Auction Theory and Applications #Bayesian Modeling and Causal Inference #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge #Multiagent Systems (cs.MA) #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2010.12327
openalex publication_date 2020/10/23 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Future coalition operations can be substantially augmented through agile\nteaming between human and machine agents, but in a coalition context these\nagents may be unfamiliar to the human users and expected to operate in a broad\nset of scenarios rather than being narrowly defined for particular purposes. In\nsuch a setting it is essential that the human agents can rapidly build trust in\nthe machine agents through appropriate transparency of their behaviour, e.g.,\nthrough explanations. The human agents are also able to bring their local\nknowledge to the team, observing the situation unfolding and deciding which key\ninformation should be communicated to the machine agents to enable them to\nbetter account for the particular environment. In this paper we describe the\ninitial steps towards this human-agent knowledge fusion (HAKF) environment\nthrough a recap of the key requirements, and an explanation of how these can be\nfulfilled for an example situation. We show how HAKF has the potential to bring\nvalue to both human and machine agents working as part of a distributed\ncoalition team in a complex event processing setting with uncertain sources.\n